© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 70036
    Prev
    Next
    INDEX
    Explanations

    commands, next actions, or specific situations

    np_acts-logits-general · gemini-2.5-flash-lite

    explanation of terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elling
    0.53
    n
    0.53
    als
    0.52
    pt
    0.51
    yl
    0.51
    ology
    0.51
    ll
    0.50
    m
    0.50
    px
    0.50
    lt
    0.49
    POSITIVE LOGITS
     possiamo
    0.50
     devemos
    0.50
     hicimos
    0.49
    ષ્ટ
    0.49
     prevenir
    0.49
     podamos
    0.48
     internalization
    0.48
     dobbiamo
    0.48
     implica
    0.47
     ہوسکتا
    0.47
    Activations Density 0.002%

    No Known Activations